© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12042
    Prev
    Next
    INDEX
    Explanations

    select or highlight items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CallCheck
    -0.21
     Rh
    -0.19
    .isLoading
    -0.19
    YST
    -0.19
    .linkedin
    -0.18
    ersed
    -0.18
     Kings
    -0.18
    .OP
    -0.18
    .isAuthenticated
    -0.18
    /engine
    -0.18
    POSITIVE LOGITS
    grab
    0.22
    éĢī
    0.21
    çĬ¶æĢģä¸ĭ
    0.21
    ä¸Ńå¼ı
    0.20
    èµĭ
    0.20
    æݧèĤ¡éĽĨåĽ¢
    0.19
     bach
    0.19
    æĦŁè§¦
    0.19
    åĨįåİ»
    0.19
     ObjectId
    0.19
    Activations Density 0.166%

    No Known Activations